EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

End-to-end simulation of nanopore sequencing signals with feed-forward transformers

Denis Beslic iD, Martin Kucklick iD, Susanne Engelmann iD, Stephan Fuchs iD, Bernhard Y Renard iD, Nils Körber iD

Bioinformatics · 26.12.2024 · 41 (1)

DOI: 10.1093/bioinformatics/btae744 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 23.12.2024. Verfasst von Denis Beslic und 5 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Artificial Intelligence in Public Health Research, Robert Koch Institute, Berlin 13353, Germany. Hauptthemen laut MEDLINE: Nanopore Sequencing, Sequence Analysis, DNA, Nanopores. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Nanopore sequencing represents a significant advancement in genomics, enabling direct long-read DNA sequencing at the single-molecule level. Accurate simulation of nanopore sequencing signals from nucleotide sequences is crucial for method development and for complementing experimental data. Most existing approaches rely on predefined statistical models, which may not adequately capture the properties of experimental signal data. Furthermore, these simulators were developed for earlier versions of nanopore chemistry, which limits their applicability and adaptability to the latest flow cell data. Results To enhance the quality of artificial signals, we introduce seq2squiggle, a novel transformer-based, non-autoregressive model designed to generate nanopore sequencing signals from nucleotide sequences. Unlike existing simulators that rely on static k-mer models, our approach learns sequential contextual information from segmented signal data. We benchmark seq2squiggle against state-of-the-art simulators on real experimental R9.4.1 and R10.4.1 data, evaluating signal similarity, basecalling accuracy, and variant detection rates. Seq2squiggle consistently outperforms existing tools across multiple datasets, demonstrating superior similarity to real data and offering a robust solution for simulating nanopore sequencing signals with the latest flow cell generation. Availability and implementation seq2squiggle is freely available on GitHub at: github.com/ZKI-PH-ImageAnalysis/seq2squiggle.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Nanopore SequencingSequence Analysis, DNANanoporesAlgorithmsComputer SimulationSoftware

Autor:innen und Institutionen

  • Centre for Artificial Intelligence in Public Health Research, Robert Koch Institute, Berlin 13353, Germany.
  • Institute for Microbiology, Technical University of Braunschweig, Braunschweig 38106, Germany.
  • Microbial Proteomics, Helmholtz Centre for Infection Research (HZI), Braunschweig 38124, Germany.
  • Genome Competence Center, Robert Koch Institute, Berlin 13353, Germany.
  • Data Analytics and Computational Statistics, Hasso Plattner Institute, Digital Engineering Faculty, University of Potsdam, Potsdam 14482, Germany.

ORCID-Profile: Denis Beslic, Martin Kucklick, Susanne Engelmann, Stephan Fuchs, Bernhard Y Renard, Nils Körber

Zitieren

APA

Beslic, D., Kucklick, M., Engelmann, S., Fuchs, S., Renard, B. Y., & Körber, N. (2024). End-to-end simulation of nanopore sequencing signals with feed-forward transformers. Bioinformatics, 41(1). https://doi.org/10.1093/bioinformatics/btae744

Vancouver

Beslic D, Kucklick M, Engelmann S, Fuchs S, Renard BY, Körber N. End-to-end simulation of nanopore sequencing signals with feed-forward transformers. Bioinformatics. 2024;41(1). doi:10.1093/bioinformatics/btae744

BibTeX
@article{Beslic2024,
  author = {Beslic, Denis and Kucklick, Martin and Engelmann, Susanne and Fuchs, Stephan and Renard, Bernhard Y and Körber, Nils},
  title = {End-to-end simulation of nanopore sequencing signals with feed-forward transformers},
  journal = {Bioinformatics},
  year = {2024},
  volume = {41},
  number = {1},
  doi = {10.1093/bioinformatics/btae744}
}
Kostenlos starten →